Validation of a deep learning-based AI model for breast cancer risk stratification in postmenopausal ER+/HER2-breast cancer patients

Q: What problem does the study address with the Nottingham Histological Grade (NHG) system?

NHG has interobserver variability, and its three-group structure overrepresents an intermediate group, where prognosis varies widely. This makes individualized treatment planning challenging.

Q: How was the Stratipath AI model validated in this study?

The study analyzed clinical data from 2466 postmenopausal ER+/HER2- breast cancer patients who did not receive chemotherapy. NHG and Stratipath were compared using concordance index and hazard ratios for distant recurrence.

Q: What were the main findings when comparing Stratipath with NHG?

Stratipath’s five-risk group model predicted distant recurrence with performance similar to NHG (c-index 0.71 vs 0.72). Stratipath risk groups 2–5 showed significantly increased hazard ratios for distant recurrence compared with NHG risk comparisons reported in the results.

Sep 28, 2026

Uploaded by Lucas Martin

Breast cancer prognostication is essential for treatment decisions, yet the Nottingham Histological Grade (NHG) system shows interobserver variability and overrepresents the intermediate risk group, complicating individualized planning. This study validated Stratipath’s low/high-risk categories and five risk groups and compared its performance with NHG. Using clinical data from 2466 postmenopausal ER+/HER2- patients without chemotherapy, distant recurrence prediction was assessed via concordance index and hazard ratios.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Article info

Abstract

Introduction

The Breast 85 (2026) 104671 Contents lists available at ScienceDirect The Breast journal [homepage:](homepage: www.journals.elsevier.com/the-breast)[ www.journals.elsevier.com/the-breast](homepage: www.journals.elsevier.com/the-breast) | Validation of a deep learning-based AI model for breast cancer risk stratification in postmenopausal ER+/HER2-breast cancer patients
Sandra Sinius Pouplier a,b,* , Abhinav Sharmac , Pekka Ruusuvuorid, Johan Hartman e, Maj-Britt Jensen f, Bent Ejlertsen b,f,g, Mattias Rantalainenc, Anne-Vibeke Lænkholm a,b
a Department of Surgical Pathology, Zealand University Hospital, Sygehusvej 10, 4000, Roskilde, Denmark
b Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, Blegdamsvej 3B, 2200, Copenhagen N, Denmark c Department of Medical Epidemiology and Biostatistics, Nobels V¨ag 12A, 171 77 Stocholm, Karolinska Institute, Sweden
d Institute of Biomedicine, University of Turku, Kiinamyllynkatu 10, 20520, Turku, Finland
e Department of Oncology-Pathology, Karolinska Institute, Solnav¨agen 30, 171 64 Solna, Sweden
f Danish Breast Cancer Group, Department of Oncology, Centre for Cancer and Organ Disease, Rigshospitalet, Blegdamsvej 9, Copenhagen University Hospital, 2100, Copenhagen, Denmark
g Department of Oncology, Centre for Cancer and Organ Disease, Rigshospitalet, Blegdamsvej 9, Copenhagen University Hospital, Denmark | | | | | --- | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Breast cancer Prognostication AI-models Deep learning Stratipath breast
Survival analysis | | Background: Breast cancer prognostication is crucial for treatment decisions, and the Nottingham Histologic Grade (NHG) system is widely used. However, NHG suffers from interobserver variability, and its division into three risk groups leaves the intermediate group (comprising ~50 % of patients) overrepresented, making individualized treatment planning challenging as prognosis within this group differ widely.
Objectives: This study aimed to validate the prognostic value of Stratipath’s low and high-risk categories and five risk groups and compare NHG performance with the Stratipath deep-learning-based model.
Methods: We analyzed clinical data from 2466 postmenopausal, ER+/HER2-breast cancer patients who did not receive chemotherapy according to guidelines at that time. The NHG and Stratipath models were compared using concordance index and hazard ratios (HR) for distant recurrence (DR), with time to any recurrence (TR) and overall survival (OS) as secondary endpoints.
Results: The Stratipath five-risk group model showed similar performance to the NHG-system in predicting DR (cindex 0.71 vs. 0.72). HR for DR for Stratipath risk groups 2, 3, 4, and 5 were 1.91 (95 % CI: 1.17–3.13), 2.63 (95 % CI: 1.63–4.24), 3.18 (95 % CI: 2.00–5.07), and 3.25 (95 % CI: 2.00–5.28), respectively (p < 0.0001). In the NHG 2 subgroup, Stratipath Breast retained prognostic value for DR (HR for groups 3–5 vs. group 1: 1.73–1.85; p = 0.05), with a c-index of 0.71.
Conclusions: The Stratipath AI model performs similarly to the NHG system. Further prospective validation of the clinical benefits of differentiating Stratipath risk groups 2 and 3 in treatment strategies would be valuable. | | 1. Introduction Pathology departments worldwide are undergoing a digital transformation, shifting from traditional slide assessment under the microscope to digital pathology. This transition enables improved collaboration among pathologists and the integration of new technologies [1]. Precise cancer treatment is essential to improve survival while minimizing the risk of overtreatment, which can lead to long-term adverse effects and negatively impact the quality of life for long-term survivors. When a patient is diagnosed with breast cancer (BC), multidisciplinary team (MDT) conferences decide on an individualized treatment plan. These discu

FAQs

What problem does the study address with the Nottingham Histological Grade (NHG) system?

NHG has interobserver variability, and its three-group structure overrepresents an intermediate group, where prognosis varies widely. This makes individualized treatment planning challenging.

How was the Stratipath AI model validated in this study?

The study analyzed clinical data from 2466 postmenopausal ER+/HER2- breast cancer patients who did not receive chemotherapy. NHG and Stratipath were compared using concordance index and hazard ratios for distant recurrence.

What were the main findings when comparing Stratipath with NHG?

Stratipath’s five-risk group model predicted distant recurrence with performance similar to NHG (c-index 0.71 vs 0.72). Stratipath risk groups 2–5 showed significantly increased hazard ratios for distant recurrence compared with NHG risk comparisons reported in the results.

Sep 28, 2026

Uploaded by Lucas Martin